INDEX

Explanations

texts related to programming and technical instructions

oai_token-act-pair · gpt-3.5-turbo

actions or plans related to discussion or explanation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Canaveral

-0.75

 helicopter

-0.66

 Civic

-0.65

 Keystone

-0.64

 valve

-0.63

 Helic

-0.62

 helicopters

-0.61

 Allies

-0.61

 ripple

-0.60

 Corinth

-0.60

POSITIVE LOGITS

endix

0.98

 "$:/

0.92

Ĥ¬

0.88

escription

0.83

ĵĺ

0.82

ģĸ

0.81

 delve

0.79

uploads

0.79

claimer

0.78

ĻĤ

0.78

Activations Density 0.644%

texts related to programming and technical instructions

actions or plans related to discussion or explanation

No Comments

No Known Activations